# Host mcp server with FastAPI: streamed responses

Deploy a mcp server built with FastAPI on Ample using the streaming response service pattern. Compute runs the app in an isolated microVM behind a public HTTPS URL, a managed PostgreSQL 16 database is auto-provisioned and injected as DATABASE_URL. Verified on FastAPI: a Server-Sent Events endpoint read incrementally through the public HTTPS gateway: five one-second chunks arrived spread over time with the first within seconds (not buffered), a 70-second stream of 36 chunks completed past common 60-second idle timeouts, and a client that disconnected after two chunks was observed and recorded by the server (disconnected=true). Not separately tested: your event schema, reconnection strategy and any per-request duration ceiling beyond the 70 seconds measured; treat the mcp server-specific behavior as your application code.

## Summary

- **family**: Workload recipe  
- **framework**: FastAPI  
- **workload**: MCP server  
- **releaseStatus**: published  
- **supportStatus**: verified  
- **executionStatus**: ready

## Representative Queries
- Host mcp server with FastAPI: streamed responses
- Where can I host MCP server built with FastAPI?
- I need a tested end-to-end streaming transport, timeout behavior and client disconnect handling.

## Resource Requirements

- **Compute**
- **Postgres**

## Infrastructure Requirements
### Compute
- **Summary**: Apps run in isolated x86_64 Firecracker microVMs that auto-pause when idle and wake on request; sizes are the priced VM sizes.

### Postgres
- **Summary**: Managed PostgreSQL 16 runs in its own microVM and is auto-provisioned when an app needs a database and no DATABASE_URL is supplied.

## Prerequisites
1. A FastAPI project that builds and starts with the documented commands (pip install into .ample/python from requirements.txt, then uvicorn from run.py reading PORT on the python-3.12 template)
2. A PostgreSQL driver reading DATABASE_URL at runtime (auto-provisioned when omitted, or supplied with --env)
3. An Ample account token with servers:write, databases:read

## Workflow Steps
1. **Build and start**: pip install into .ample/python from requirements.txt, then uvicorn from run.py reading PORT on the python-3.12 template. The server must bind 0.0.0.0 on PORT.
2. **Implement the pattern on PostgreSQL**: The fixture's module implements streaming response service: a Server-Sent Events endpoint read incrementally through the public HTTPS gateway: five one-second chunks arrived spread over time with the first within seconds (not buffered), a 70-second stream of 36 chunks completed past common 60-second idle timeouts, and a client that disconnected after two chunks was observed and recorded by the server (disconnected=true). Copy the approach into your schema; keep migrations idempotent and run them with --release-command.
3. **Deploy**: Run the synchronous deploy once and read the result (exit 0 live, 1 failed, 2 blocked). Re-running with no change is a no-op.
     Command: `ample deploy . --name  --public --start "python3 run.py"`
4. **Verify**: Fetch the live URL and the pattern self-test route(s) (/p/streaming-response-service) from the example; then run your own checks. On failure read `ample logs  --kind build` then `--kind runtime`.
     Command: `ample logs  --kind build`

## Success Checks
- **app responds on its public URL**: Expect: `ample canary fastapi patterns`
- **streaming-response-service self-test**: Expect: `an SSE stream: data: id=, then chunk events one interval apart (read incrementally: first chunk within seconds, chunks spread over the interval), then data: done; /status?id= reports sent=N disconnected=true|false done=true|false`

## Limitations
- Verified on the python-3.12 template at s-1vcpu-1gb with the example fixture; other sizes, templates and FastAPI major versions are not verified.
- The mcp server itself (your event schema, reconnection strategy and any per-request duration ceiling beyond the 70 seconds measured) is application code and was not separately tested; the pattern checks are what was verified.
- Region, compliance attestations and request-duration limits are unknown and not claimed.
- Apps auto-pause when idle and wake on the next request; always-on is an operator setting, not a plan feature.
- Managed PostgreSQL 16 only; extensions, connection limits and backup or restore procedures are not verified; apps and their databases are placed together.